A Raspberry Pi Pico 2 W runs compact game worlds and learning agents
Technology · First reported 29 Oct, 20:32 · Updated 00:33
A project uses two small neural networks to simulate and play five simple games on a Raspberry Pi Pico 2 W. Its creator reports that the models fit the device’s memory and can be checked against the games’ real rules.
- The world model predicts the next game frame and reward from the current frame and an action; a separate actor selects actions from generated frames. Both run on the Pico 2 W.
- The system covers Breakout, Doom-lite, Flappy Bird, Pong and Pac-Man lite. At two transformer loops, reported exact-frame accuracy ranges from 83.6% for Doom-lite to 100% for Flappy Bird.
- The project describes int8 world-model weights and on-device learning. It reports that its largest game configuration, Pac-Man, uses 600 KB of flash and 460 KB of SRAM.
Summary written by Lux AI from 2 articlesUnverified
Key facts
- Device
- Raspberry Pi Pico 2 W
- Games
- Breakout, Doom-lite, Flappy Bird, Pong and Pac-Man lite
- World-model accuracy at two loops
- 83.6% for Doom-lite; 100% for Flappy Bird
- Largest listed game configuration
- Pac-Man: 600 KB flash and 460 KB SRAM
Source spectrum
Far left
Left
Lean left
Centre
Lean right
Right
Far right
Unrated
Left 0 · Centre 1 · Right 0 of 1 rated sources · +1 unrated
Background
All coverage
Coverage over time
LeftCentreRight
Articles per hour since first reported, by side.
Ownership
- Corporation 50% (1)
- Unknown 50% (1)
Share of the 2 sources by owner type.